arrow
返回

Reference-Based OCT Angiogram Super-Resolution With Learnable Texture Generation

delete2024-01-01
delete0
PRE
AI
Y
Yuyan Ruan
D
Dawei Yang
Z
Ziqi Tang
A
An Ran Ran
J
Jiguang Wang
C
Carol Y. Cheung
H
Hao Chen *
DOI:10.1109/TNNLS.2024.3456483delete
delete原文链接
delete分享
delete收藏
摘要

摘要

En 中文
Optical coherence tomography angiography (OCTA) can visualize retinal microvasculature and is important to qualitatively and quantitatively identify potential biomarkers for different retinal diseases. However, the resolution of optical coherence tomography (OCT) angiograms inevitably decreases when increasing the field-of-view (FOV) given a fixed acquisition time. To address this issue, we propose a novel reference-based super-resolution (RefSR) framework to preserve the resolution of the OCT angiograms while increasing the scanning area. Specifically, textures from the normal RefSR pipeline are used to train a learnable texture generator (LTG), which is designed to generate textures according to the input. The key difference between the proposed method and traditional RefSR models is that the textures used during inference are generated by the LTG instead of being searched from a single reference (Ref) image. Since the LTG is optimized throughout the whole training process, the available texture space is significantly enlarged and no longer limited to a single Ref image, but extends to all textures contained in the training samples. Moreover, our proposed LTGNet does not require an Ref image at the inference phase, thereby becoming invulnerable to the selection of the Ref image. Both experimental and visual results show that LTGNet has competitive performance and robustness over state-of-the-art methods, indicating good reliability and promise in real-life deployment.
Keyword:
Retina
Training
Superresolution
Image reconstruction
Visualization
Technological innovation
Transformers
Robustness
Learning systems
Feature extraction
Deep learning
optical coherence tomography angiography (OCTA)
reference-based super-resolution (RefSR)
retina
texture generation

期刊

IEEE Transactions on Neural Networks and Learning Systems 封面图
IEEE Transactions on Neural Networks and Learning Systems
IF:
8.9
论文数:
7.8K
被引数:
9.0W

机构

香
香港中文大學
学者数:
49
论文数: 23
被引数: 2.6W
引用论文

引用论文

暂无论文信息